Sam Leighton

Thanks to coauthors including @benjaminperry.bsky.social @rajkd.bsky.social @dmachlanski.bsky.social @stsaftaris.bsky.social on BlueSky!

Check out our new article using causal mediation analysis to show that early (0–12 week) weight gain drives the 1‑year impact of antipsychotics on weight. We then used counterfactual prediction to model “what if” treatment scenarios - a step toward personalised prevention.
doi.org/10.1192/bjp....

Our proposal for a session at @rcpsych.bsky.social congress has been accepted. Looking forward to speaking on the future of precision psychiatry with @rajkd.bsky.social @dmachlanski.bsky.social and Fani Deligianni. Here's a taster of what we're talking about!

Cool that makes sense. Cheers

Is this still as problematic if they regress out the weight at baseline? In this paper they don't seem to do that, rather the control of recent weight change which isn't the same thing.

Dynamic prediction with prediction of counterfactuals for individualised decisions. Really cool.

First week 'critical' to avoid children missing school later, parents told Data suggests more than half of children who miss a day at the start of term become persistently absent.

A fantastic teaching example of a predictor being misinterpreted as having a causal effect.

#CausalSky #EpiSky

I also have this issue - no moderation despite preprints being available for months. It will significantly reduce the utility of psyarxiv if moderation takes the same time as peer review for an actual journal. There will be little point in submitting to preprint at psyarxiv if this is the case.

New causal prediction feasibility study preprint with I Lam Leong, @dmachlanski.bsky.social @benjaminperry.bsky.social @stsaftaris.bsky.social Fani Deligianni, Stephen M Lawrie and @rajkd.bsky.social

Check out our new preprint: Antipsychotic-induced weight gain in psychosis – a causal mediation analysis and feasibility study of casual actionable prediction model development using counterfactuals to target obesity osf.io/preprints/ps... #CausalSky

Mazel Tov

Ethnic Bias in Prediction and Decision Making Algorithms in Precision Psychiatry: Challenges in a Shrinking World - Journal of Psychosocial Rehabilitation and Mental Health This article examines ethnic bias in predictive algorithms and decision-making systems within precision psychiatry. While these models aim to provide individualised outcomes and improve healthcare, th...

link.springer.com/article/10.1...

Check out the new preprint with @rajkd.bsky.social @stsaftaris.bsky.social and Fani Deligianni
A fallacy at the heart of precision medicine - are current clinical prediction models actionable? osf.io/preprints/ps... #CausalSky

Thanks. I would love to attend but unfortunately have clinical duties at the time.

Will this be recorded and available after the webinar?

Check out the new preprint with @rajkd.bsky.social @stsaftaris.bsky.social and Fani Deligianni
A fallacy at the heart of precision medicine - are current clinical prediction models actionable? osf.io/preprints/ps... #CausalSky

NEW PAPER in @bmj.com where we discuss the rationale, challenges, and approaches to providing uncertainty
of risk estimates from clinical prediction models

www.bmj.com/content/388/...

#StatsSky #MLSky #EpiSky #AI #machinelearning

Me and @rajkd.bsky.social published a paper on precision psychiatry www.cambridge.org/core/journal...